|
import math |
|
import numpy as np |
|
import torch |
|
import torch.nn as nn |
|
from PIL import Image, ImageDraw |
|
|
|
|
|
def autopad(k, p=None): |
|
|
|
if p is None: |
|
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] |
|
return p |
|
|
|
|
|
class DepthSeperabelConv2d(nn.Module): |
|
""" |
|
DepthSeperable Convolution 2d with residual connection |
|
""" |
|
|
|
def __init__(self, inplanes, planes, kernel_size=3, stride=1, downsample=None, act=True): |
|
super(DepthSeperabelConv2d, self).__init__() |
|
self.depthwise = nn.Sequential( |
|
nn.Conv2d(inplanes, inplanes, kernel_size, stride=stride, groups=inplanes, padding=kernel_size//2, bias=False), |
|
nn.BatchNorm2d(inplanes, momentum=BN_MOMENTUM) |
|
) |
|
|
|
|
|
|
|
self.pointwise = nn.Sequential( |
|
nn.Conv2d(inplanes, planes, 1, bias=False), |
|
nn.BatchNorm2d(planes, momentum=BN_MOMENTUM) |
|
) |
|
self.downsample = downsample |
|
self.stride = stride |
|
try: |
|
self.act = nn.Hardswish() if act else nn.Identity() |
|
except: |
|
self.act = nn.Identity() |
|
|
|
def forward(self, x): |
|
|
|
|
|
out = self.depthwise(x) |
|
out = self.act(out) |
|
out = self.pointwise(out) |
|
|
|
if self.downsample is not None: |
|
residual = self.downsample(x) |
|
out = self.act(out) |
|
|
|
return out |
|
|
|
|
|
|
|
class SharpenConv(nn.Module): |
|
|
|
def __init__(self, c1, c2, k=3, s=1, p=None, g=1, act=True): |
|
super(SharpenConv, self).__init__() |
|
sobel_kernel = np.array([[-1, -1, -1], [-1, 8, -1], [-1, -1, -1]], dtype='float32') |
|
kenel_weight = np.vstack([sobel_kernel]*c2*c1).reshape(c2,c1,3,3) |
|
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False) |
|
self.conv.weight.data = torch.from_numpy(kenel_weight) |
|
self.conv.weight.requires_grad = False |
|
self.bn = nn.BatchNorm2d(c2) |
|
try: |
|
self.act = nn.Hardswish() if act else nn.Identity() |
|
except: |
|
self.act = nn.Identity() |
|
|
|
def forward(self, x): |
|
return self.act(self.bn(self.conv(x))) |
|
|
|
def fuseforward(self, x): |
|
return self.act(self.conv(x)) |
|
|
|
|
|
class Conv(nn.Module): |
|
|
|
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): |
|
super(Conv, self).__init__() |
|
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False) |
|
self.bn = nn.BatchNorm2d(c2) |
|
try: |
|
self.act = nn.Hardswish() if act else nn.Identity() |
|
except: |
|
self.act = nn.Identity() |
|
|
|
def forward(self, x): |
|
return self.act(self.bn(self.conv(x))) |
|
|
|
def fuseforward(self, x): |
|
return self.act(self.conv(x)) |
|
|
|
|
|
class Bottleneck(nn.Module): |
|
|
|
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): |
|
super(Bottleneck, self).__init__() |
|
c_ = int(c2 * e) |
|
self.cv1 = Conv(c1, c_, 1, 1) |
|
self.cv2 = Conv(c_, c2, 3, 1, g=g) |
|
self.add = shortcut and c1 == c2 |
|
|
|
def forward(self, x): |
|
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) |
|
|
|
|
|
class BottleneckCSP(nn.Module): |
|
|
|
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): |
|
super(BottleneckCSP, self).__init__() |
|
c_ = int(c2 * e) |
|
self.cv1 = Conv(c1, c_, 1, 1) |
|
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False) |
|
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False) |
|
self.cv4 = Conv(2 * c_, c2, 1, 1) |
|
self.bn = nn.BatchNorm2d(2 * c_) |
|
self.act = nn.LeakyReLU(0.1, inplace=True) |
|
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)]) |
|
|
|
def forward(self, x): |
|
y1 = self.cv3(self.m(self.cv1(x))) |
|
y2 = self.cv2(x) |
|
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1)))) |
|
|
|
|
|
class SPP(nn.Module): |
|
|
|
def __init__(self, c1, c2, k=(5, 9, 13)): |
|
super(SPP, self).__init__() |
|
c_ = c1 // 2 |
|
self.cv1 = Conv(c1, c_, 1, 1) |
|
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) |
|
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) |
|
|
|
def forward(self, x): |
|
x = self.cv1(x) |
|
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) |
|
|
|
|
|
class Focus(nn.Module): |
|
|
|
|
|
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): |
|
super(Focus, self).__init__() |
|
self.conv = Conv(c1 * 4, c2, k, s, p, g, act) |
|
|
|
def forward(self, x): |
|
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)) |
|
|
|
|
|
class Concat(nn.Module): |
|
|
|
def __init__(self, dimension=1): |
|
super(Concat, self).__init__() |
|
self.d = dimension |
|
|
|
def forward(self, x): |
|
""" print("***********************") |
|
for f in x: |
|
print(f.shape) """ |
|
return torch.cat(x, self.d) |
|
|
|
|
|
class Detect(nn.Module): |
|
stride = None |
|
|
|
def __init__(self, nc=13, anchors=(), ch=()): |
|
super(Detect, self).__init__() |
|
self.nc = nc |
|
self.no = nc + 5 |
|
self.nl = len(anchors) |
|
self.na = len(anchors[0]) // 2 |
|
self.grid = [torch.zeros(1)] * self.nl |
|
a = torch.tensor(anchors).float().view(self.nl, -1, 2) |
|
self.register_buffer('anchors', a) |
|
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) |
|
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) |
|
|
|
def forward(self, x): |
|
z = [] |
|
for i in range(self.nl): |
|
x[i] = self.m[i](x[i]) |
|
|
|
bs, _, ny, nx = x[i].shape |
|
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous() |
|
|
|
|
|
if not self.training: |
|
if self.grid[i].shape[2:4] != x[i].shape[2:4]: |
|
self.grid[i] = self._make_grid(nx, ny).to(x[i].device) |
|
y = x[i].sigmoid() |
|
|
|
|
|
|
|
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i].to(x[i].device)) * self.stride[i] |
|
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] |
|
"""print("**") |
|
print(y.shape) #[1, 3, w, h, 85] |
|
print(y.view(bs, -1, self.no).shape) #[1, 3*w*h, 85]""" |
|
z.append(y.view(bs, -1, self.no)) |
|
return x if self.training else (torch.cat(z, 1), x) |
|
|
|
@staticmethod |
|
def _make_grid(nx=20, ny=20): |
|
|
|
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)]) |
|
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float() |
|
|
|
|
|
"""class Detections: |
|
# detections class for YOLOv5 inference results |
|
def __init__(self, imgs, pred, names=None): |
|
super(Detections, self).__init__() |
|
d = pred[0].device # device |
|
gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs] # normalizations |
|
self.imgs = imgs # list of images as numpy arrays |
|
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls) |
|
self.names = names # class names |
|
self.xyxy = pred # xyxy pixels |
|
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels |
|
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized |
|
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized |
|
self.n = len(self.pred) |
|
|
|
def display(self, pprint=False, show=False, save=False): |
|
colors = color_list() |
|
for i, (img, pred) in enumerate(zip(self.imgs, self.pred)): |
|
str = f'Image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} ' |
|
if pred is not None: |
|
for c in pred[:, -1].unique(): |
|
n = (pred[:, -1] == c).sum() # detections per class |
|
str += f'{n} {self.names[int(c)]}s, ' # add to string |
|
if show or save: |
|
img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img # from np |
|
for *box, conf, cls in pred: # xyxy, confidence, class |
|
# str += '%s %.2f, ' % (names[int(cls)], conf) # label |
|
ImageDraw.Draw(img).rectangle(box, width=4, outline=colors[int(cls) % 10]) # plot |
|
if save: |
|
f = f'results{i}.jpg' |
|
str += f"saved to '{f}'" |
|
img.save(f) # save |
|
if show: |
|
img.show(f'Image {i}') # show |
|
if pprint: |
|
print(str) |
|
|
|
def print(self): |
|
self.display(pprint=True) # print results |
|
|
|
def show(self): |
|
self.display(show=True) # show results |
|
|
|
def save(self): |
|
self.display(save=True) # save results |
|
|
|
def __len__(self): |
|
return self.n |
|
|
|
def tolist(self): |
|
# return a list of Detections objects, i.e. 'for result in results.tolist():' |
|
x = [Detections([self.imgs[i]], [self.pred[i]], self.names) for i in range(self.n)] |
|
for d in x: |
|
for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']: |
|
setattr(d, k, getattr(d, k)[0]) # pop out of list""" |